Feature Extraction
sentence-transformers
Safetensors
Transformers
qwen3
text-generation
sentence-similarity
text-embeddings-inference
Instructions to use Qwen/Qwen3-Embedding-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Qwen/Qwen3-Embedding-0.6B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Qwen/Qwen3-Embedding-0.6B") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use Qwen/Qwen3-Embedding-0.6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Qwen/Qwen3-Embedding-0.6B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Embedding-0.6B") model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Embedding-0.6B") - Inference
- Notebooks
- Google Colab
- Kaggle
Tom Aarsen commited on
Commit ·
2653833
1
Parent(s): 2f6ecfd
Remove eod_id line from README
Browse files
README.md
CHANGED
|
@@ -145,7 +145,6 @@ model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B')
|
|
| 145 |
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
|
| 146 |
# model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B', attn_implementation="flash_attention_2", torch_dtype=torch.float16).cuda()
|
| 147 |
|
| 148 |
-
eod_id = tokenizer.convert_tokens_to_ids("<|endoftext|>")
|
| 149 |
max_length = 8192
|
| 150 |
|
| 151 |
# Tokenize the input texts
|
|
|
|
| 145 |
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
|
| 146 |
# model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B', attn_implementation="flash_attention_2", torch_dtype=torch.float16).cuda()
|
| 147 |
|
|
|
|
| 148 |
max_length = 8192
|
| 149 |
|
| 150 |
# Tokenize the input texts
|